Triple
T36283863
| Position | Surface form | Disambiguated ID | Type / Status |
|---|---|---|---|
| Subject | Steven Schachter |
E893017
|
entity |
| Predicate | directedTelevisionFilm |
P111223
|
FINISHED |
| Object | Door to Door |
—
|
NE NERFINISHED |
How this triple was built (2 steps)
Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.
NER
Named-entity recognition
gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: Door to Door | Statement: [Steven Schachter, directedTelevisionFilm, Door to Door]
PD
Predicate disambiguation
gpt-5-mini-2025-08-07
Target predicate: directedTelevisionFilm Context triple: [Steven Schachter, directedTelevisionFilm, Door to Door]
-
A.
directedTVShow
Indicates that a person served as the director of a particular television show.
-
B.
directedIn
chosen
Indicates that one entity served as the director of another entity, such as a person directing a film, episode, or similar work.
-
C.
televisionFilm
Indicates that the subject is a television film (a movie produced for or originally distributed via television).
-
D.
hasDirectedTelevision
Indicates that one entity has directed a television production, such as a TV show or episode, involving the other entity.
-
E.
directedFilmInFranchise
Indicates that a person served as the director of a specific film that is part of a particular franchise.
- F. None of above.
Provenance (3 batches)
The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.
| Step | Stage | Batch ID | Status | When |
|---|---|---|---|---|
| creating | Elicitation | batch_69f76e4955c08190b8cfddca34fc0242 |
completed | May 3, 2026, 3:48 p.m. |
| NER | Named-entity recognition | batch_69fe21b0cba48190b56c39e9f1c0eafa |
completed | May 8, 2026, 5:47 p.m. |
| PD | Predicate disambiguation | batch_69fe204576848190aecf204e2adba5dc |
completed | May 8, 2026, 5:41 p.m. |
Created at: May 3, 2026, 4:09 p.m.